From f11c29260eb068114172b08d8e88b1e113df1a3a Mon Sep 17 00:00:00 2001 From: yisding Date: Thu, 29 Feb 2024 14:57:39 -0800 Subject: [PATCH] minor doc updates --- docs/getting_started/v0_10_0_migration.md | 6 +++--- docs/index.rst | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/getting_started/v0_10_0_migration.md b/docs/getting_started/v0_10_0_migration.md index b25cfb29022e2..27d5bc6390134 100644 --- a/docs/getting_started/v0_10_0_migration.md +++ b/docs/getting_started/v0_10_0_migration.md @@ -2,9 +2,9 @@ With the introduction of LlamaIndex v0.10.0, there were several changes -- integrations have separate `pip installs (See the [full registry](https://pretty-sodium-5e0.notion.site/ce81b247649a44e4b6b35dfb24af28a6?v=53b3c2ced7bb4c9996b81b83c9f01139)) +- integrations have separate `pip install`s (See the [full registry](https://pretty-sodium-5e0.notion.site/ce81b247649a44e4b6b35dfb24af28a6?v=53b3c2ced7bb4c9996b81b83c9f01139)) - many imports changed -- the service context was deprecated +- the `ServiceContext` was deprecated Thankfully, we've tried to make these changes as easy as possible! @@ -72,7 +72,7 @@ from llama_index.core import Settings Settings.llm = llm Settings.embed_model = embed_model -Setting.chunk_size = 512 +Settings.chunk_size = 512 ``` You can see the `ServiceContext` -> `Settings` migration guide for [more details](/module_guides/supporting_modules/service_context_migration.md). diff --git a/docs/index.rst b/docs/index.rst index 7799e24493afb..ea8fe43e671c5 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -19,7 +19,7 @@ You may choose to **fine-tune** a LLM with your data, but: - Due to the cost to train, it's **hard to update** a LLM with latest information. - **Observability** is lacking. When you ask a LLM a question, it's not obvious how the LLM arrived at its answer. -Instead of fine-tuning, one can a context augmentation pattern called `Retrieval-Augmented Generation (RAG) <./getting_started/concepts.html>`_ to obtain more accurate text generation relevant to your specific data. RAG involves the following high level steps: +Instead of fine-tuning, one can use a context augmentation pattern called `Retrieval-Augmented Generation (RAG) <./getting_started/concepts.html>`_ to obtain more accurate text generation relevant to your specific data. RAG involves the following high level steps: 1. Retrieve information from your data sources first, 2. Add it to your question as context, and @@ -36,7 +36,7 @@ In doing so, RAG overcomes all three weaknesses of the fine-tuning approach: Firstly, LlamaIndex imposes no restriction on how you use LLMs. You can still use LLMs as auto-complete, chatbots, semi-autonomous agents, and more (see Use Cases on the left). It only makes LLMs more relevant to you. -LlamaIndex provides the following tools to help you quickly standup production-ready RAG systems: +LlamaIndex provides the following tools to help you quickly stand up production-ready RAG systems: - **Data connectors** ingest your existing data from their native source and format. These could be APIs, PDFs, SQL, and (much) more. - **Data indexes** structure your data in intermediate representations that are easy and performant for LLMs to consume. @@ -70,7 +70,7 @@ We recommend starting at `how to read these docs <./getting_started/reading.html To download or contribute, find LlamaIndex on: -- Github: https://github.com/jerryjliu/llama_index +- Github: https://github.com/run-llama/llama_index - PyPi: - LlamaIndex: https://pypi.org/project/llama-index/.